贝叶斯深度学习论文趋势 2023–2026

主要结论

• 贝叶斯深度学习论文从 2023 年的 112 篇增长到 2026 年的 112 篇，三年间扩大到约 1.0 倍。
• NeurIPS 是发贝叶斯深度学习论文最多的会议，2023–2026 年共 165 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是驾驶仿真：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 11 篇。
• 在「概率与贝叶斯」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的高斯过程是 2.2 倍，贝叶斯深度学习是 1.0 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Approximate Bayesian inference with exchangeable distributions for neurosymbolic AI
• ICML 2026A Bayesian Approach to Quantify the Uncertainty of Human Ratings in a Single-Instance Multimodal Framework
• ICLR 2026Bayesian Neural Networks for Functional ANOVA Model
• CVPR 2026CGU-Bayes Causal Graph Uncertainty-Guided Bayesian Inference for Domain Generalization
• NeurIPS 2025A Bayesian Approach to Contextual Dynamic Pricing using the Proportional Hazards Model with Discrete Price Data
• ICML 2025BARNN: A Bayesian Autoregressive and Recurrent Neural Network
• ICLR 2025Bayesian Image Regression with Soft-thresholded Conditional Autoregressive Prior
• CVPR 2025HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories
• NeurIPS 2024Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
• ICML 2024Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification
• ICLR 2024A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors
• CVPR 2024Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
• NeurIPS 2023A Bayesian Approach To Analysing Training Data Attribution In Deep Learning
• ICML 2023Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?
• ICLR 2023Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference
• CVPR 2023Bayesian Posterior Approximation With Stochastic Ensembles
• NeurIPS 2026BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation
• ICML 2026Bayesian Gated Non-Negative Contrastive Learning
• ICLR 2026Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
• CVPR 2026Evidential Deep Partial Label Learning to Quantify Disambiguation Uncertainty

全部贝叶斯深度学习论文

共 408 篇，第 2 / 9 页

51. ICML 2026LILO: Bayesian Optimization with Natural Language Feedback
52. ICML 2026Local Constrained Bayesian Optimization
53. ICML 2026Log-Normal Multiplicative Dynamics for Stable Low-Precision Deep Learning
54. ICML 2026Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
55. ICML 2026On the Epistemic Uncertainty of Overparametrized Neural Networks
56. ICML 2026On the Expressive Power of Permutation-Equivariant Weight-Space Networks
57. ICML 2026Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs
58. ICML 2026Predictive variational inference: Learn the predictively optimal posterior distribution
59. ICML 2026Probabilistically-routed Bayesian Additive Spanning Trees for Learning on Constrained Domains
60. ICML 2026Proximal-IMH: Proximal Posterior Proposals for Independent Metropolis–Hastings with Approximate Operators
61. ICML 2026Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
62. ICML 2026Richer Bayesian Last Layers with Subsampled NTK Features
63. ICML 2026Robust Bayesian Optimisation with Unbounded Corruptions
64. ICML 2026Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation
65. ICML 2026SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning
66. ICML 2026Singular Bayesian Neural Networks
67. ICML 2026Sparse Bayesian Deep Functional Learning with Structured Region Selection
68. ICML 2026Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space
69. ICML 2026Symmetries in PAC-Bayesian Learning
70. ICML 2026TabMGP: Martingale Posterior with TabPFN
71. ICML 2026Taking the GP Out of the Loop
72. ICML 2026Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
73. NeurIPS 2026A Revisit of Hamiltonian Monte Carlo Efficiency on Bayesian Neural Networks
74. NeurIPS 2026Approximate Bayesian inference with exchangeable distributions for neurosymbolic AI
75. NeurIPS 2026Bayes-pFCL:Bayesian Personalized Federated Continual Learning
76. NeurIPS 2026Bayesian Causal Experimental Design for CATE Estimation under Noncompliance
77. NeurIPS 2026Bayesian Causal Stress Testing: Posterior Fragility of Treatment-Effect Conclusions
78. NeurIPS 2026Bayesian Low-Rank Posteriors for Scalable Membership Inference
79. NeurIPS 2026Bayesian Preference Learning for Test-Time Steerable Reward Models
80. NeurIPS 2026Bifurcation Models: Learning Set-Valued Solution Maps with Weight-Tied Dynamics
81. NeurIPS 2026BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation
82. NeurIPS 2026CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification
83. NeurIPS 2026CLUE: Correlated Latent Uncertainty for Single-Pass Deep Uncertainty Estimation
84. NeurIPS 2026DnNP: Denoising Input Uncertainty in Neural Processes
85. NeurIPS 2026Does Weight Decay Enhance Training Stability?
86. NeurIPS 2026DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization
87. NeurIPS 2026Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
88. NeurIPS 2026Ensemble Distributionally Robust Bayesian Optimisation
89. NeurIPS 2026ESS-Flow: training-free guidance as Bayesian inference in source space
90. NeurIPS 2026Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
91. NeurIPS 2026Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
92. NeurIPS 2026Generative Active Learning via Bayesian Acquisition for Improving the Efficiency of Synthetic Data
93. NeurIPS 2026Incorporating Neural Network Structure in the Bayesian Learning Rule
94. NeurIPS 2026Maximin Robust Bayesian Experimental Design
95. NeurIPS 2026Neural Bayesian Filtering
96. NeurIPS 2026On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets
97. NeurIPS 2026On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference
98. NeurIPS 2026On the Existence of Uniformly Optimal Policies in MDPs under Epistemic Uncertainty
99. NeurIPS 2026Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems
100. NeurIPS 2026Position: Semantic Uncertainty Measures Disagreement, Not Reliability

常见问题

2023–2026 年四大会议一共有多少篇贝叶斯深度学习论文？

共 408 篇，按年份分别是 2023 年 112 篇、2024 年 100 篇、2025 年 84 篇、2026 年 112 篇。

NeurIPS 2026 有多少篇贝叶斯深度学习论文？

NeurIPS 2026 有 40 篇贝叶斯深度学习论文，上一届是 27 篇。

ICLR 2026 有多少篇贝叶斯深度学习论文？

ICLR 2026 有 22 篇贝叶斯深度学习论文，上一届是 30 篇。

ICML 2026 有多少篇贝叶斯深度学习论文？

ICML 2026 有 41 篇贝叶斯深度学习论文，上一届是 24 篇。

CVPR 2026 有多少篇贝叶斯深度学习论文？

CVPR 2026 有 9 篇贝叶斯深度学习论文，上一届是 3 篇。

哪个会议的贝叶斯深度学习论文最多？

NeurIPS，2023–2026 年共 165 篇。